Add 0.75 ensemble evaluation support and workflow enhancements#343
Merged
sgreenbury merged 3 commits intomainfrom Apr 22, 2026
Merged
Add 0.75 ensemble evaluation support and workflow enhancements#343sgreenbury merged 3 commits intomainfrom
sgreenbury merged 3 commits intomainfrom
Conversation
Add a dedicated ensemble-size ambient eval submitter for the 75% quarter checkpoint and keep its outputs isolated under an eval_0p75 work directory. Extend the eval workflow CLI with an output subdirectory option so these partial-schedule runs can reuse the normal wrapper without mixing logs, videos, or metrics with the canonical final-checkpoint evals.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request adds support for specifying a custom evaluation output subdirectory in the workflow, which allows evaluation results to be organized under different folders (e.g., for partial-schedule checkpoints). The main changes include updating the CLI, command logic, and tests to handle the new
--output-subdirargument, and adding a new SLURM script for evaluating 75%-schedule checkpoints.Evaluation output directory customization:
--output-subdirargument (default:"eval") to theevalCLI command, allowing users to specify a custom subdirectory for evaluation outputs. [1] [2]build_eval_overridesandeval_commandincommands.pyto use the specifiedoutput_subdirinstead of hardcoding"eval". [1] [2] [3]New evaluation script for partial checkpoints:
slurm_scripts/ablations/ensemble_size/eval_0p75/submit_eval_crps_ambient.sh, which evaluates the 75%-schedule (third quarter) checkpoints and outputs results to an isolatedeval_0p75/directory.README.mdto explain the new script and the organization of evaluation outputs for ensemble-size ablation runs. [1] [2]